© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-RES-MATRYOSHKA-DC
    7. 2647
    Prev
    Next
    INDEX
    Explanations

    technical descriptions of circuits and situations where someone didn't get a response.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.22.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ftagPool
    -0.60
    ITHUB
    -0.59
    EDEFAULT
    -0.59
    #
    -0.58
    UrlResolution
    -0.57
    expandindo
    -0.57
    tanleria
    -0.57
     Paglinawan
    -0.56
    bitField
    -0.56
    /-/
    -0.53
    POSITIVE LOGITS
     response
    3.09
     respond
    2.80
     reply
    2.77
     responses
    2.77
     Response
    2.73
     réponse
    2.69
     answer
    2.66
    response
    2.64
     responded
    2.63
     responds
    2.61
    Activations Density 1.266%

    No Known Activations